EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Probabilistic Forecasting and Information-Theoretic Analysis of Multivariate fMRI Dynamics

Arda Bayer iD, Zhiyao Zhang iD, Ahmet Emre Ipek iD, Rose Khavari iD, Behnaam Aazhang iD

Entropy · 01.07.2026 · 28 (7) · 738

DOI: 10.3390/e28070738 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 01.07.2026. Verfasst von Arda Bayer und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical & Computer Engineering, Rice University, Houston, TX 77005, USA. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Rice University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Functional magnetic resonance imaging (fMRI) signals exhibit complex temporal structure arising from multivariate neural dynamics, physiological variability, and measurement uncertainty. In this work, we formulate region-of-interest-level fMRI analysis as a probabilistic multi-step forecasting problem and investigate the predictability of blood-oxygen-level-dependent (BOLD) activity from an information-theoretic perspective. Using the Natural Scenes Dataset, we model multiregional BOLD activity as a stochastic process with finite memory and train multiple forecasting architectures, including linear regression, exponential smoothing, recurrent neural networks, and transformer-based models, to predict future BOLD samples from preceding temporal observations. Forecasting performance is analyzed together with entropy-based quantities, including marginal entropy, conditional entropy, and normalized predictive information measures estimated directly from model-derived predictive distributions without imposing restrictive Gaussian assumptions on the underlying BOLD dynamics. The transformer model achieved significant improvement over a naive persistence baseline (p=0.001) while yielding a high predictive information fraction (η=75.49%). Post hoc directed information analysis revealed that short-horizon prediction was dominated primarily by autoregressive, within-ROI, temporal structure. Overall, the proposed framework demonstrates how probabilistic forecasting and information-theoretic analysis can be integrated to characterize the predictability, uncertainty structure, and directional organization of large-scale fMRI dynamics and may support future downstream neuroengineering and neural-state inference applications.

Schlagwörter

Stichwörter der Autor:innen

BOLD signalbrain dynamicsdirected informationentropyfunctional magnetic resonance imaginginformation theoryprobabilistic forecastingrecurrent neural networksstochastic processestransformer models

Autor:innen und Institutionen

  • Department of Electrical & Computer Engineering, Rice University, Houston, TX 77005, USA.
  • Department of Electrical & Electronics Engineering, Özyeğin University, 34794 Istanbul, Türkiye.
  • Department of Urology, Houston Methodist, Houston, TX 77030, USA.

ORCID-Profile: Arda Bayer, Zhiyao Zhang, Ahmet Emre Ipek, Rose Khavari, Behnaam Aazhang

Förderung

  • Rice University

Zitieren

APA

Bayer, A., Zhang, Z., Ipek, A. E., Khavari, R., & Aazhang, B. (2026). Probabilistic Forecasting and Information-Theoretic Analysis of Multivariate fMRI Dynamics. Entropy, 28(7), 738. https://doi.org/10.3390/e28070738

Vancouver

Bayer A, Zhang Z, Ipek AE, Khavari R, Aazhang B. Probabilistic Forecasting and Information-Theoretic Analysis of Multivariate fMRI Dynamics. Entropy. 2026;28(7):738. doi:10.3390/e28070738

BibTeX
@article{Bayer2026,
  author = {Bayer, Arda and Zhang, Zhiyao and Ipek, Ahmet Emre and Khavari, Rose and Aazhang, Behnaam},
  title = {Probabilistic Forecasting and Information-Theoretic Analysis of Multivariate fMRI Dynamics},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {7},
  pages = {738},
  doi = {10.3390/e28070738}
}
Kostenlos starten →